# Air Toxicity and Chronic Respiratory Diseases (US) — Data

来源：https://www.kaggle.com/competitions/air-toxicity-and-chronic-respiratory-diseases-us/data

采集时间：2026-10-19T10:52:40Z

# Dataset Description for "Air Toxicity and Chronic Respiratory Diseases (US)"

Welcome to the dataset description page for the Kaggle competition "Air Toxicity and Chronic Respiratory Diseases (US)". Here we provide detailed information about the data files, format, the prediction task and definitions of acronyms used.

## Files

- **train.csv** - This is the training set, which you will use to build your models. It contains various features along with the target variable that represents the prevalence of chronic respiratory diseases.

- **test.csv** - The test set contains the same features as the training set but without the target variable. You will use this to generate your predictions.

- **sample_submission.csv** - This is a sample submission file in the correct format. It includes all the IDs from the test set and assumes a constant prediction for the target variable.

- **State.Names.csv** - This file provides a list of all U.S states referenced in the data.

- **supplementary_*.parquet** - These are supplementary files containing additional features that can be merged with the main training and test sets based on the 'example_id'.

## Columns

### train.csv

- `ID` - The ID representing each record in the dataset. This ID is consistent across `train.csv`, `test.csv`, and the supplementary files.

- `State.Name` - The name of the U.S. state where the data was recorded.

- `Year` - The year when the data was recorded.

- `Age` - The age group of the elderly population for which the data is recorded. Age is grouped into ranges, for example, "65-69", "70-74", etc.

- `Incidence` - This is the target variable representing the incidence rate of chronic respiratory diseases in the given age group. This means how many new cases there are in a year divided by how many people there are in the middle of the year.

### test.csv

- `ID` - The ID representing each record in the dataset. This ID is consistent across `train.csv`, `test.csv`, and the supplementary files.

- `State.Name` - The name of the U.S. state where the data was recorded.

- `Year` - The year when the data was recorded.

- `Age` - The age group of the elderly population for which the data is recorded. Age is grouped into ranges, for example, "65-69", "70-74", etc.

### supplementary_*.parquet

- `State.Name` - The name of the U.S. state where the data was recorded.

- `Date.Local` - The local date when the measurements were taken.

- `Parameter.Name` - The name or description assigned in AQS to the parameter measured by the monitor. Parameters may be pollutants or non-pollutants.

- `Arithmetic.Mean` - The average (arithmetic mean) value for the year for the given parameter.

- `X1st.Max.Value` - The highest value for the year for the given parameter.

## Data Cleaning
Data cleaning was performed using the following GitHub repository: [Data Cleaning](https://github.com/josephcmac/chronic-respiratory-diseases)